© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129806
    Prev
    Next
    INDEX
    Explanations

    punctuation and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     decorado
    -1.89
     we
    -1.77
    gantung
    -1.76
     decorados
    -1.70
     hermosas
    -1.70
     excelentes
    -1.68
     Füßen
    -1.68
    ֢
    -1.66
     שלנו
    -1.66
     reciclado
    -1.64
    POSITIVE LOGITS
     and
    2.16
     (
    2.02
     in
    1.92
    ar
    1.71
     at
    1.69
    懂得
    1.63
     as
    1.54
     a
    1.53
     also
    1.52
    诟
    1.48
    Activations Density 0.082%

    No Known Activations